arXiv:2606. 10678v1 Announce Type: new Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies.
By Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers, M. M. Lutfe Elahi, Sifat Momen, Nabeel Mohammed, Shafin Rahman
arXiv:2505. 15354v3 Announce Type: replace Abstract: Time-series forecasting is a critical task in various business domains, but it remains inherently challenging.
By Hamza Cherkaoui, Malik Tiomoko, Giuseppe Paolo, Zhang Yili, Yu Meng, Zhang Keli, Hafiz Tiomoko Ali
The paper introduces Forecast‑Aware Residual Refinement (FARR), a method that refines long‑horizon time‑series forecasts by learning to correct predictions using endpoint evidence. FARR generates a valid forecast under normal conditions and a null forecast under a predefined null condition; the difference between these forecasts indicates how auxiliary conditioning affects the prediction. A shared residual refiner then combines this endpoint evidence with historical features to estimate the remaining error, and horizon‑wise gating controls the contribution of the predicted residual to the final output. Experiments on four long‑horizon benchmarks demonstrate that FARR achieves the best average MSE and MAE among compared methods.
By Yiyang Zhang, Yuli Zheng, Bin Li, Meimei Zhang, Qiang Sun
The paper introduces Forecast‑Aware Residual Refinement (FARR), a method that corrects time‑series forecasts by learning from endpoint evidence. FARR generates a valid forecast under normal conditions and a null forecast under a predefined null condition; the difference between them indicates how conditioning affects the prediction. A shared residual refiner then combines this evidence with historical features to estimate and gate the remaining forecast error, achieving superior MSE and MAE on four long‑horizon benchmarks.
arXiv:2512.22428v3 Announce Type: replace
Abstract: Post-hoc residual correction can reduce forecasting error, but always-on updates often fail to generalize: when residual signals are weak or noisy,...
By Jianxiang Xie, Yuncheng Hua, Mingyue Cheng, Flora D. Salim, Hao Xue
arXiv:2602. 02288v3 Announce Type: replace Abstract: Current time-series forecasting models are primarily based on transformer-style neural networks.
By Zheng Li, Jerry Cheng, Huanying Gu
RATL is a plug‑in method for multivariate time‑series forecasting that uses a frozen base forecaster to build a memory of its historical forecast residuals. During inference, RATL retrieves residual trajectories from similar past contexts and employs a set‑aware router to combine them, providing learned feedback correction. Experiments demonstrate that this residual‑retrieval approach improves the performance of the base forecaster across various benchmarks and backbones.
By Yuchen He, Yueyang Cang, Zhiyuan Ning, Ningyu Wang, Li Shi
Irregular multivariate time series forecasting (IMTSF) requires capturing temporal dynamics and cross-variable dependencies from sparse, asynchronous observations. Existing methods often rely on learn...
arXiv:2607. 17511v1 Announce Type: new Abstract: Large \emph{Time Series Foundation Models} (TSFMs) demonstrate strong zero-shot forecasting capabilities across diverse domains.
By Wentao Gao, Jiuyong Li, Lin Liu, Thuc Duy Le, Jixue Liu, Yanchang Zhao, Yun Chen
Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that capacity is what unlocks accuracy. We take the opposite position: most of the gap can be closed at far lower cost by tuning preprocessing rather than scaling models.
arXiv:2606. 27282v1 Announce Type: new Abstract: Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that capacity is what unlocks accuracy.
By Lang Huang, Jinglue Xu, Luke Darlow
AdaRDiff is a new adaptive reversible differencing technique for time‑series forecasting that learns weighted differencing to remove trend and seasonality, stabilizes residuals for forecasting, and then reconstructs the forecast autoregressively. The method offers a closed‑form convolutional implementation that can be GPU‑parallelized, achieving up to 33.7× speedup over naive recurrence. Experiments on eight diverse benchmarks show state‑of‑the‑art accuracy and significant performance gains when integrated into various backbone models, from linear models to Transformers.
By Morad Laglil, Younes Hlal, Marouane El Hadari, Emilie Devijver, Eric Gaussier